mlsanityData to 14 Oct 2026

CDT: Cascading Decision Trees for Explainable Reinforcement Learning

arXiv 2011.07553 ↗First posted 15 Nov 2020cs.LGcited by 15

Not on the map. Why?

Abstract (arXiv)

Deep Reinforcement Learning (DRL) has recently achieved significant advances in various domains. However, explaining the policy of RL agents still remains an open problem due to several factors, one being the complexity of explaining neural networks decisions. Recently, a group of works have used decision-tree-based models to learn explainable policies. Soft decision trees (SDTs) and discretized differentiable decision trees (DDTs) have been demonstrated to achieve both good performance and share the benefit of having explainable policies. In this work, we further improve the results for tree-based explainable RL in both performance and explainability. Our proposal, Cascading Decision Trees (CDTs) apply representation learning on the decision path to allow richer expressivity. Empirical results show that in both situations, where CDTs are used as policy function approximators or as imitation learners to explain black-box policies, CDTs can achieve better performances with more succinct and explainable models than SDTs. As a second contribution our study reveals limitations of explaining black-box policies via imitation learning with tree-based explainable models, due to its inherent instability.

Key facts. Cited by 15 papers in the map (data through 14 Oct 2026). First posted on arXiv 15 Nov 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 4; 2023: 3; 2024: 5; 2025: 0; 2026: 3.

15 papers.

Sort:

By area:

  1. 2023Consistency Models as a Rich and Efficient Policy Class for Reinforcement Learningcited by 100
  2. 2022POETREE: Interpretable Policy Learning with Adaptive Decision Treescited by 14
  3. 2022MIXRTs: Toward Interpretable Multi-Agent Reinforcement Learning via Mixing Recurrent Soft Decision Treescited by 11
  4. 2022Explainability in Deep Reinforcement Learning, a Review into Current Methods and Applicationscited by 6
  5. 2024Vanilla Gradient Descent for Oblique Decision Treescited by 6
  6. 2023Synthesizing Programmatic Policies with Actor-Critic Algorithms and ReLU Networkscited by 3
  7. 2024SkillTree: Explainable Skill-Based Deep Reinforcement Learning for Long-Horizon Control Taskscited by 3
  8. 2024Solving Offline Reinforcement Learning with Decision Tree Regressioncited by 2
  9. 2024RGMDT: Return-Gap-Minimizing Decision Tree Extraction in Non-Euclidean Metric Spacecited by 2
  10. 2022Knowledge Distillation Decision Tree for Unravelling Black-box Machine Learning Modelscited by 1
  11. 2024Three Pathways to Neurosymbolic Reinforcement Learning with Interpretable Model and Policy Networkscited by 1
  12. 2023Can Differentiable Decision Trees Enable Interpretable Reward Learning from Human Feedback?cited by 0
3 more
  1. 2026Approximation-Free Differentiable Oblique Decision Treescited by 0
  2. 2026Reinforcement Learning: From Algorithms To Foundation Modelscited by 0
  3. 2026Explainable Reinforcement Learning for assisting Air Traffic Controllerscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Optimizing Interpretable Decision Tree Policies for Reinforcement Learning
  2. 2023Optimal Decision Tree Policies for Markov Decision Processes
  3. 2018Verifiable Reinforcement Learning via Policy Extraction
  4. 2024Mitigating Information Loss in Tree-Based Reinforcement Learning via Direct Optimization
  5. 2024Putting the Iterative Training of Decision Trees to the Test on a Real-World Robotic Task
  6. 2025Interpretable reinforcement learning for heat pump control through asymmetric differentiable decision trees
  7. 2026Interpretable reinforcement learning with decision-tree pruning
  8. 2026Explainably Safe Reinforcement Learning